LTS4/universal

Stars
235
Rank 171,079 (Top 4 %)
Language
MATLAB
Created almost 8 years ago
Updated almost 6 years ago

LTS4/universal

LTS4

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Universal adversarial perturbations

matlab: MATLAB code to generate universal perturbations, using Caffe or MatConvNet.

python: Python code to generate universal perturbations using TensorFlow.

precomputed: Precomputed universal perturbations, for pre-trained models on ImageNet.

Reference

[1] S. Moosavi-Dezfooli*, A. Fawzi*, O. Fawzi, P. Frossard: Universal adversarial perturbations, CVPR 2017

DeepFool

A simple and accurate method to fool deep neural networks

SparseFool

A fast sparse attack on deep neural networks.

hold-me-tight

Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"

neural-anisotropy-directions

Source code for "Neural Anisotropy Directions"

TIGraNet

PyTorch implementation of TIGraNet

gnn_statistics

Code for the paper "On the choice of graph neural network architectures"

deepfool_caffe

C++ implementation of the DeepFool algorithm on top of Caffe with MATLAB API

OrthoNet

A general approach for multilayer network data clustering

Jupyter Notebook

DASH_Optimal_Set

ILP problem to optimize the representations set in DASH systems

graph-learning

Collection of models for learning networks from signals.

seizure_eeg